© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 31561
    Prev
    Next
    INDEX
    Explanations

    Articles followed by actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¸įæ³ķ
    -0.08
    _finalize
    -0.07
    erman
    -0.07
    abase
    -0.07
    zas
    -0.07
     buf
    -0.07
    说ä¸į
    -0.06
    ä¹Ŀéĩį
    -0.06
    建设æĪIJ为
    -0.06
    为æĤ¨æݨèįIJ
    -0.06
    POSITIVE LOGITS
    ombres
    0.08
    _or
    0.07
    代ä¼ļ
    0.07
    -or
    0.06
    ideshow
    0.06
    _inline
    0.06
    æıĽ
    0.06
     ÃĹ
    0.06
    ierzch
    0.06
     конеÑĩно
    0.06
    Activations Density 0.489%

    No Known Activations